Exploratory_Visuals_03_18
Connie Xu
3/18/2021
##
## The downloaded binary packages are in
## /var/folders/gs/080wb67j58df5y8ccjf53yw00000gn/T//RtmpelCG7i/downloaded_packages##
## The downloaded binary packages are in
## /var/folders/gs/080wb67j58df5y8ccjf53yw00000gn/T//RtmpelCG7i/downloaded_packages##
## The downloaded binary packages are in
## /var/folders/gs/080wb67j58df5y8ccjf53yw00000gn/T//RtmpelCG7i/downloaded_packages## Error in get(genname, envir = envir) : object 'testthat_print' not foundR Markdown
This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.
When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:
## Warning: Missing column names filled in: 'X1' [1]##
## ── Column specification ─────────────────────────────────────────────────────────────────────────────────────────────────
## cols(
## .default = col_double(),
## INSTNM = col_character(),
## CITY = col_character(),
## STABBR = col_character(),
## ZIP = col_character(),
## UNEMP_RATE = col_logical(),
## DEBT_MDN = col_character(),
## MN_EARN_WNE_P10 = col_logical(),
## MD_EARN_WNE_P10 = col_logical(),
## ADM_RATE_ALL_1 = col_character()
## )
## ℹ Use `spec()` for the full column specifications.## # A tibble: 1,269 x 24
## X1 UNITID INSTNM CITY state ZIP lat long ADM_RATE CONTROL ACTCMMID
## <dbl> <dbl> <chr> <chr> <chr> <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 0 100654 Alaba… Norm… AL 35762 34.8 -86.6 0.899 1 18
## 2 1 100663 Unive… Birm… AL 3529… 33.5 -86.8 0.921 1 25
## 3 3 100706 Unive… Hunt… AL 35899 34.7 -86.6 0.809 1 28
## 4 4 100724 Alaba… Mont… AL 3610… 32.4 -86.3 0.977 1 18
## 5 5 100751 The U… Tusc… AL 3548… 33.2 -87.5 0.591 1 27
## 6 7 100830 Aubur… Mont… AL 3611… 32.4 -86.2 0.928 1 21
## 7 8 100858 Aubur… Aubu… AL 36849 32.6 -85.5 0.754 1 28
## 8 9 100937 Birmi… Birm… AL 35254 33.5 -86.9 0.567 2 26
## 9 10 101189 Faulk… Mont… AL 3610… 32.4 -86.2 0.523 2 21
## 10 14 101435 Hunti… Mont… AL 3610… 32.4 -86.3 0.584 2 22
## # … with 1,259 more rows, and 13 more variables: SAT_AVG <dbl>, COSTT4_A <dbl>,
## # UNEMP_RATE <lgl>, DEBT_MDN <chr>, MN_EARN_WNE_P10 <lgl>,
## # MD_EARN_WNE_P10 <lgl>, UGDS_WHITE <dbl>, UGDS_BLACK <dbl>, UGDS_HISP <dbl>,
## # UGDS_ASIAN <dbl>, UGDS_AIAN <dbl>, UGDS_NHPI <dbl>, ADM_RATE_ALL_1 <chr>## [1] "X1" "UNITID" "INSTNM" "CITY"
## [5] "state" "ZIP" "lat" "long"
## [9] "ADM_RATE" "CONTROL" "ACTCMMID" "SAT_AVG"
## [13] "COSTT4_A" "UNEMP_RATE" "DEBT_MDN" "MN_EARN_WNE_P10"
## [17] "MD_EARN_WNE_P10" "UGDS_WHITE" "UGDS_BLACK" "UGDS_HISP"
## [21] "UGDS_ASIAN" "UGDS_AIAN" "UGDS_NHPI" "ADM_RATE_ALL_1"
## [25] "uni_rank"# | variable | description |
# | :----------------------- | --------------------------------------------------------- |
# | UNITID | IPEDS Unit ID |
# | CITY | description |
# | state | state |
# | DEBT_MDN | The median original amount of the |
# | | loan principal upon entering repayment |Selectivity is based on Conwell et al. (2022 exp.) [1]
Including Plots
#note
us <- map_data("state")
us_states <- as_data_frame(us) %>% dplyr::rename(state=region)
us_states## # A tibble: 15,537 x 6
## long lat group order state subregion
## <dbl> <dbl> <dbl> <int> <chr> <chr>
## 1 -87.5 30.4 1 1 alabama <NA>
## 2 -87.5 30.4 1 2 alabama <NA>
## 3 -87.5 30.4 1 3 alabama <NA>
## 4 -87.5 30.3 1 4 alabama <NA>
## 5 -87.6 30.3 1 5 alabama <NA>
## 6 -87.6 30.3 1 6 alabama <NA>
## 7 -87.6 30.3 1 7 alabama <NA>
## 8 -87.6 30.3 1 8 alabama <NA>
## 9 -87.7 30.3 1 9 alabama <NA>
## 10 -87.8 30.3 1 10 alabama <NA>
## # … with 15,527 more rowsmapping=aes(x = lat, y = long)
ggplot(us, aes(x = long, y = lat, group=group)) +
geom_polygon(aes(), color='white') +
theme_ipsum() + theme(panel.grid = element_blank())+ geom_point(data = df, aes(x = long, y = lat, group=UNITID),color='orange',alpha=0.5) 
dfsub <- df %>% subset(DEBT_MDN != 'PrivacySuppressed') %>% drop_na(uni_rank) %>% drop_na(DEBT_MDN)
dfsub$uni_rank_cat = factor(dfsub$uni_rank, levels=c('elite','highly selective','selective','less selective','not selective'))
ggplot(dfsub, aes(x=uni_rank_cat,y=DEBT_MDN)) +
geom_point(color = '#87495F',alpha=.12) +
theme_ipsum(base_size = 12, axis_title_size = 14) +
theme(
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()) +
ggtitle("Student Debt and School Tiers") +
labs(fill = "Selectivity", y="Student Debt", x = "School Competitiveness")
#dfsub %>% group_by(uni_rank) %>% mutate(density = n())
m <- ggplot(dfsub, aes(x=DEBT_MDN,y=UGDS_BLACK, color = uni_rank_cat)) +
geom_point(aes(color = uni_rank_cat), alpha=.5) +
scale_color_manual(values=c("#F7F5F4","#786D77","#82809A","#87495F","#211622"))+
geom_smooth(method = lm, se = FALSE)+
theme_ipsum() +
theme(
panel.grid.major = element_blank(),
panel.grid.minor = element_blank()) +
ggtitle("Student Debt and Racial Composition (Black Students)") +
labs(y="% Black Students", x = "Median Student Debt ($)")
ggplotly(m)echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.—
[1] - Conwell, Jordan A. and Natasha Quadlin. Forthcoming. “Race, Gender,Higher Education, and Socioeconomic Attainment: Evidence from Baby Boomers at Mid-Life.” Social Forces. DOI: 10.1093/sf/soab010.